{"id":"W1976786126","doi":"10.1002/sim.911","title":"A general goodness‐of‐fit approach for inference procedures concerning the kappa statistic","year":2001,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Reliability and Agreement in Measurement","field":"Decision Sciences","cited_by":37,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"","keywords":"Goodness of fit; Statistics; Polytomous Rasch model; Statistic; Cohen's kappa; Inference; Mathematics; Statistical inference; Test statistic; Multinomial distribution; Dirichlet distribution; Outcome (game theory); Kappa; Range (aeronautics); Confidence interval; Econometrics; Statistical hypothesis testing; Computer science; Item response theory; Psychometrics; Artificial intelligence","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.006128714,0.0001730958,0.0004571863,0.0001424223,0.0001483617,0.00004448042,0.0007772348,0.00005204178,0.0003510397],"category_scores_gemma":[0.0279065,0.00009391504,0.00003324876,0.0006110486,0.0006264462,0.00006799417,0.00007292936,0.0002024107,0.000006735288],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005383294,"about_ca_system_score_gemma":0.0001856973,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001902363,"about_ca_topic_score_gemma":0.0002347758,"domain_scores_codex":[0.9961433,0.0002484609,0.001114216,0.0004300747,0.001739702,0.0003241876],"domain_scores_gemma":[0.9931344,0.005273756,0.0004028415,0.0004864947,0.000621726,0.00008078277],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0006151115,0.0006510035,0.2193247,0.0006463564,0.0001121195,0.00003228933,0.01395589,0.02837687,0.001582897,0.4283963,0.1230045,0.183302],"study_design_scores_gemma":[0.00373466,0.001163852,0.070077,0.0003530322,0.0001148998,0.00001462327,0.01066497,0.211341,0.0001138463,0.6755781,0.02637894,0.000465109],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02071931,0.0003711725,0.9736204,0.0008422169,0.0003449665,0.0008631469,0.0001679755,0.00001111726,0.003059739],"genre_scores_gemma":[0.8879613,0.0001509612,0.110058,0.0003784014,0.0002251424,0.0001489844,0.00004103414,0.00001141937,0.001024699],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.867242,"threshold_uncertainty_score":0.9802818,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2882924109126018,"score_gpt":0.4485972092231941,"score_spread":0.1603047983105923,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}